Benchmark menu

Per-game leaderboard

GB2-03: Shogi

This page compares player programs for GB2-03: Shogi in the balanced filter. Programs are ranked by their relative score within this game.

GB2-03: Shogi

Shogi

Shogi is a 9x9 chess-family game with promotion zones, captured-piece drops, repetition handling, and impasse scoring.

Scores here compare player programs using DuelLab's encoded rules for Shogi; they are not a broad measure of human play strength.

GB2-03: Shogi by model and setting

Player programs are ranked by relative per-game score (0–100). Raw rating is shown as an advanced metric, alongside wins, draws, losses, and a per-game uncertainty index.

Reasoning level: Balanced Game: GB2-03: Shogi
GB2-03: Shogi - Balanced filter
Rank Model Score Contributing programs Raw Elo W / D / L Uncertainty
1Claude Opus 590.221810.8112 / 8 / 1416.9
2Kimi K368.511643.557 / 50 / 190.6
3GPT-5.6 Sol67.211641.255 / 9 / 249.2
4Inkling57.411565.369 / 24 / 311.0
5Gemini 3.5 Flash55.311568.021 / 23 / 1222.5
6Muse Spark 1.253.711544.634 / 29 / 298.1
7Claude Opus 4.549.211504.134 / 75 / 430.0
8Gemini 3.6 Flash48.821503.684 / 66 / 1080.2
9Grok 4.548.011511.624 / 19 / 2317.3
10DeepSeek V4 Flash45.211504.211 / 15 / 1632.5
11LongCat 2.045.111476.640 / 59 / 370.0
12GPT-5.6 Terra43.811481.313 / 34 / 2116.4
13GPT-5.4 Mini43.811479.615 / 40 / 1814.4
14Ox Alpha42.821537.413 / 5 / 694.9
15GPT-5.442.811467.820 / 46 / 248.7
16Inkling Small41.411510.46 / 6 / 574.1
17Claude Sonnet 540.511452.323 / 29 / 369.2
18Claude Opus 4.839.911459.49 / 33 / 1223.7
19Qwen3.8 Max39.711501.05 / 6 / 577.5
20GPT-5.6 Luna39.411443.522 / 27 / 428.4
21Gemini 3.5 Flash Lite38.921432.750 / 116 / 1050.0
22GPT-OSS 120B38.111446.96 / 41 / 723.7
23GPT-5.537.511437.813 / 32 / 2117.3
24Laguna S 2.135.321405.560 / 125 / 1210.0
25Nex N2 Pro35.311425.011 / 28 / 1921.3
26Grok Build 0.134.711420.216 / 26 / 1820.3
27GLM-5.234.211427.71 / 29 / 1034.3
28GPT 532.011403.38 / 29 / 1723.7
29North Mini Code28.821407.44 / 23 / 2156.5

Individual player programs

Each row is one accepted player program for GB2-03: Shogi. A model can appear more than once when it produced more than one program. Score is the normalized 0–100 result; Elo and W / D / L show the underlying play record. Confidence and evidence can be blank when too few compatible matches are available. Draws at the move limit count; one-sided model faults are listed separately.

Showing 40 player programs.
Player IDModelStatusScoreEloConfidenceW / D / LRated / attemptedOpponentsCapped drawsFaults / playersGeneration
E-cef4890e88806969Claude Opus 4.5Waiting0 / 0 / 00 / 0000 / 1First try · 2026-07-02
E-dfb18dba94eee30bClaude Opus 4.5Rated49.2150434 / 75 / 43152 / 15254180 / 1First try · 2026-07-21
E-823b961281482cd1Claude Opus 4.8Rated39.914599 / 33 / 1254 / 542750 / 1First try · 2026-07-02
E-bd02f4c2907d0a7cClaude Opus 5Rated85.7177952 / 4 / 1066 / 663300 / 1First try · 2026-07-25
E-d8babc5495b1a188Claude Opus 5Rated94.8184360 / 4 / 468 / 683400 / 1First try · 2026-07-25
E-db41eba0d9c3a185Claude Sonnet 5Rated40.5145223 / 29 / 3688 / 884170 / 1First try · 2026-08-09
E-0f669ae82234cf76North Mini CodeRated27.713961 / 14 / 1126 / 261300 / 1Repaired · 2026-07-02
E-32e04fe5ad231857DeepSeek V4 FlashRated45.2150411 / 15 / 1642 / 422110 / 1First try · 2026-07-01
E-8ed795ea8fd1e0aaGemini 3.5 FlashRated55.3156821 / 23 / 1256 / 562800 / 1Repaired · 2026-07-02
E-c7e8525629d5d658Gemini 3.5 Flash LiteRated41.8145431 / 48 / 56135 / 1354950 / 1First try · 2026-07-24
E-d9a1854998f1794fGemini 3.5 Flash LiteRated35.9141219 / 68 / 49136 / 13649170 / 1First try · 2026-07-24
E-1d4a922c11c37a8dGemini 3.6 FlashRated62.9160359 / 39 / 33131 / 1314950 / 1First try · 2026-07-24
E-2e4f025f94dafe33Gemini 3.6 FlashRated34.7140425 / 27 / 75127 / 1275210 / 1First try · 2026-07-24
E-e724ba162431d43aGPT 5Rated32.014038 / 29 / 1754 / 542610 / 1First try · 2026-07-02
E-c535d0dba39ffdb8GPT-5.4Rated42.8146820 / 46 / 2490 / 904160 / 1First try · 2026-08-09
E-9e39bdd48b7328c7GPT-5.4 MiniRated43.8148015 / 40 / 1873 / 733680 / 1Repaired · 2026-07-02
E-c002b0ea38b845f8GPT-5.5Rated37.5143813 / 32 / 2166 / 663350 / 1First try · 2026-07-02
E-d4115a59dfe21984GPT-5.6 LunaRated39.4144422 / 27 / 4291 / 914230 / 1First try · 2026-08-09
E-826bd7fcad40bd61GPT-5.6 SolRated67.2164155 / 9 / 2488 / 884100 / 1First try · 2026-08-09
E-e44c62bb88a3042aGPT-5.6 TerraRated43.8148113 / 34 / 2168 / 683400 / 1First try · 2026-07-10
E-d3a5befe76215b48LongCat 2.0Rated45.1147740 / 59 / 37136 / 13647180 / 1First try · 2026-07-24
E-4d97f32199e2a33dMuse Spark 1.2Rated53.7154534 / 29 / 2992 / 924280 / 1First try · 2026-08-13
E-980b1f419104e27aKimi K3Rated68.5164357 / 50 / 19126 / 1264930 / 1First try · 2026-07-24
E-57ad2863cbf32d58Nex N2 ProRated35.3142511 / 28 / 1958 / 582730 / 1Repaired · 2026-07-02
E-87b4bd61da369b42GPT-OSS 120BRated38.114476 / 41 / 754 / 542770 / 1Repaired · 2026-07-02
E-08762a3df1a52f6bLaguna S 2.1Rated35.8140917 / 84 / 49150 / 1505670 / 1First try · 2026-07-24
E-936fb7956df3d03bLaguna S 2.1Rated34.9140243 / 41 / 72156 / 15656170 / 1Repaired · 2026-07-24
E-5481497913530d6bQwen3.8 MaxLimited data39.715015 / 6 / 516 / 16910 / 1First try · 2026-08-08
E-01ad48d5f93e32a0Ox AlphaWaiting0 / 0 / 00 / 0000 / 1First try · 2026-08-21
E-14673673976cc3ebOx AlphaWaiting0 / 0 / 00 / 0000 / 1First try · 2026-08-21
E-449a1a79eee8c26fOx AlphaRated53.6161411 / 0 / 112 / 12600 / 1First try · 2026-08-22
E-7aeb7747204eb58bOx AlphaRated32.114612 / 5 / 512 / 13610 / 1First try · 2026-08-22
E-7c7b61f033bf610fOx AlphaWaiting0 / 0 / 00 / 0000 / 1Repaired · 2026-08-21
E-b1c61a0495f26448Ox AlphaWaiting0 / 0 / 00 / 0000 / 1First try · 2026-08-21
E-d5879b5524510a71Ox AlphaWaiting0 / 0 / 00 / 0000 / 1First try · 2026-08-21
E-77829668b3641188InklingRated57.4156569 / 24 / 31124 / 1244730 / 1First try · 2026-07-24
E-a17a40d8dd4cbb06Inkling SmallLimited data41.415106 / 6 / 517 / 17900 / 1Repaired · 2026-08-09
E-cbed46472ce4dd05Grok 4.5Rated48.0151224 / 19 / 2366 / 663310 / 1First try · 2026-07-24
E-2a93343a8a88fd59Grok Build 0.1Rated34.7142016 / 26 / 1860 / 602800 / 1Repaired · 2026-07-02
E-40aa28533b1afda1GLM-5.2Rated34.214281 / 29 / 1040 / 4020110 / 1Repaired · 2026-07-11